Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     benefited
    -0.08
    zyć
    -0.07
    Pres
    -0.07
    Round
    -0.07
     sake
    -0.06
    asia
    -0.06
    脸
    -0.06
    Bond
    -0.06
    CBS
    -0.06
    udades
    -0.06
    POSITIVE LOGITS
     uvědom
    0.07
     transport
    0.06
     believing
    0.06
    ------------------------------------------------------------------------------------------------
    0.06
    _COMMON
    0.06
    -pe
    0.06
     barren
    0.06
    /fw
    0.06
    ]+\
    0.06
     front
    0.06
    Act Density 0.000%

    No Known Activations